SWSL ResNeXt

A ResNeXt repeats a building block that aggregates a set of transformations with the same topology. Compared to a ResNet, it exposes a new dimension, cardinality (the size of the set of transformations) \( C \), as an essential factor in addition to the dimensions of depth and width.

The models in this collection utilise semi-weakly supervised learning to improve the performance of the model. The approach brings important gains to standard architectures for image, video and fine-grained classification.

Please note the CC-BY-NC 4.0 license on theses weights, non-commercial use only.

How do I use this model on an image?

To load a pretrained model:

>>> import timm
>>> model = timm.create_model('swsl_resnext101_32x16d', pretrained=True)
>>> model.eval()

To load and preprocess the image:

>>> import urllib
>>> from PIL import Image
>>> from timm.data import resolve_data_config
>>> from timm.data.transforms_factory import create_transform

>>> config = resolve_data_config({}, model=model)
>>> transform = create_transform(**config)

>>> url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
>>> urllib.request.urlretrieve(url, filename)
>>> img = Image.open(filename).convert('RGB')
>>> tensor = transform(img).unsqueeze(0) # transform and add batch dimension

To get the model predictions:

>>> import torch
>>> with torch.inference_mode():
...     out = model(tensor)
>>> probabilities = torch.nn.functional.softmax(out[0], dim=0)
>>> print(probabilities.shape)
>>> # prints: torch.Size([1000])

To get the top-5 predictions class names:

>>> # Get imagenet class mappings
>>> url, filename = ("https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt", "imagenet_classes.txt")
>>> urllib.request.urlretrieve(url, filename)
>>> with open("imagenet_classes.txt", "r") as f:
...     categories = [s.strip() for s in f.readlines()]

>>> # Print top categories per image
>>> top5_prob, top5_catid = torch.topk(probabilities, 5)
>>> for i in range(top5_prob.size(0)):
...     print(categories[top5_catid[i]], top5_prob[i].item())
>>> # prints class names and probabilities like:
>>> # [('Samoyed', 0.6425196528434753), ('Pomeranian', 0.04062102362513542), ('keeshond', 0.03186424449086189), ('white wolf', 0.01739676296710968), ('Eskimo dog', 0.011717947199940681)]

Replace the model name with the variant you want to use, e.g. swsl_resnext101_32x16d. You can find the IDs in the model summaries at the top of this page.

To extract image features with this model, follow the timm feature extraction examples, just change the name of the model you want to use.

How do I finetune this model?

You can finetune any of the pre-trained models just by changing the classifier (the last layer).

>>> model = timm.create_model('swsl_resnext101_32x16d', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)

To finetune on your own dataset, you have to write a training loop or adapt timm's training script to use your dataset.

How do I train this model?

You can follow the timm recipe scripts for training a new model afresh.

Citation

BibTeX

@article{DBLP:journals/corr/abs-1905-00546,
  author    = {I. Zeki Yalniz and
               Herv{\'{e}} J{\'{e}}gou and
               Kan Chen and
               Manohar Paluri and
               Dhruv Mahajan},
  title     = {Billion-scale semi-supervised learning for image classification},
  journal   = {CoRR},
  volume    = {abs/1905.00546},
  year      = {2019},
  url       = {http://arxiv.org/abs/1905.00546},
  archivePrefix = {arXiv},
  eprint    = {1905.00546},
  timestamp = {Mon, 28 Sep 2020 08:19:37 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1905-00546.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}